11 papers
TRACE: Distilling Where It Matters via Token-Routed Self On-Policy Alignment
Jiaxuan Wang, Xuan Ouyang, Zhiyu Chen +4
On-policy self-distillation (self-OPD) densifies reinforcement learning with verifiable rewards (RLVR) by letting a policy teach itself under privileged context. We find that when…
PRISM: Fast Online LLM Serving via Scheduling-Memory Co-design
Xingyu Qu, Tianhao Lin, Yiqi Li +2
Modern online large language model (LLM) services, such as Retrieval-Augmented Generation (RAG) and agent systems, increasingly expose two prominent characteristics: prompt segment…
HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation
Peilin Wu, Mian Zhang, Kun Wan +4
Agentic RAG is a powerful technique for incorporating external information that LLMs lack, enabling better problem solving and question answering. However, suboptimal search behavi…
Context and Diversity Matter: The Emergence of In-Context Learning in World Models
Fan Wang, Zhiyuan Chen, Yuxuan Zhong +8
The capability of predicting environmental dynamics underpins both biological neural systems and general embodied AI in adapting to their surroundings. Yet prevailing approaches re…
Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents
Haiyang Xu, Xi Zhang, Haowei Liu +16
The paper introduces GUI-Owl-1.5, the latest native GUI agent model that features instruct/thinking variants in multiple sizes (2B/4B/8B/32B/235B) and supports a range of platforms…
LogicIF: Towards Complex Logic Instruction Following
Mian Zhang, Shujian Liu, Sixun Dong +10
Instruction following has catalyzed the recent era of Large Language Models (LLMs) and is the foundational skill underpinning more advanced capabilities such as reasoning and agent…